6 papers
Efficient Algorithms for Robust Markov Decision Processes with -Rectangular Ambiguity Sets
Chin Pang Ho, Marek Petrik, Wolfram Wiesemann
Robust Markov decision processes (MDPs) have attracted significant interest due to their ability to protect MDPs from poor out-of-sample performance in the presence of ambiguity. I…
A Note on Piecewise Affine Decision Rules for Robust, Stochastic, and Data-Driven Optimization
Simon Thomä, Maximilian Schiffer, Wolfram Wiesemann
Multi-stage decision-making under uncertainty, where decisions are taken under sequentially revealing uncertain problem parameters, is often essential to faithfully model manageria…
Don't Look Back in Anger: Wasserstein Distributionally Robust Optimization with Nonstationary Data
Dominic S. T. Keehan, Edward J. Anderson, Wolfram Wiesemann
We study data-driven decision problems where historical observations are generated by a time-evolving distribution whose consecutive shifts are bounded in Wasserstein distance. We…
It's All in the Mix: Wasserstein Classification and Regression with Mixed Features
Reza Belbasi, Aras Selvi, Wolfram Wiesemann
Problem definition: A key challenge in supervised learning is data scarcity, which can cause prediction models to overfit to the training data and perform poorly out of sample. A c…
Distributionally Robust Optimization
Daniel Kuhn, Soroosh Shafiee, Wolfram Wiesemann
Distributionally robust optimization (DRO) studies decision problems under uncertainty where the probability distribution governing the uncertain problem parameters is itself uncer…
Differential Privacy via Distributionally Robust Optimization
Aras Selvi, Huikang Liu, Wolfram Wiesemann
In recent years, differential privacy has emerged as the de facto standard for sharing statistics of datasets while limiting the disclosure of private information about the involve…